Wednesday Homework

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Cmd+Shift+Enter.

# Install packages and activating library

install.packages('tidyverse')

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.3/tidyverse_2.0.0.tgz'
Content type 'application/x-gzip' length 428470 bytes (418 KB)
==================================================
downloaded 418 KB

The downloaded binary packages are in
    /var/folders/qb/kypsbnkd3x17lyrmt3wfgwph0000gn/T//RtmpCkwRAS/downloaded_packages

library(tidyverse)

── Attaching core tidyverse packages ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.2     ✔ readr     2.1.4
✔ forcats   1.0.0     ✔ stringr   1.5.0
✔ ggplot2   3.4.3     ✔ tibble    3.2.1
✔ lubridate 1.9.2     ✔ tidyr     1.3.0
✔ purrr     1.0.2     ── Conflicts ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errors

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Cmd+Option+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Cmd+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.

# Reading in CSV File

df <- read_csv('/Users/investmentguy/Documents/python_stuff/coding_temple/week6/day3/Call of Duty Reviews.csv')

Rows: 97 Columns: 9── Column specification ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Delimiter: ","
chr (6): Game Title, Platform, Release Year, Publisher, Critic Reviews, User Reviews
dbl (3): Metascore, Critic Compound Score, User Compound Score
ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

View(df)

# Null and Alternative Hypothesis

Ho, game_title Black Ops II, leads in metascore, critic & user compound

Error: unexpected ',' in "Ho,"

# Replaced Spaces in Columns with underscores and converted all to lowercase

names(df) <- gsub(" ","_", tolower(names(df)))

df

# Checking for Null Values
colSums(is.na(df))

           game_title              platform          release_year             publisher             metascore        critic_reviews 
                    0                    16                    16                     0                    13                     9 
         user_reviews critic_compound_score   user_compound_score 
                    0                     9                     0 

# Dropping NA Values for metascore

df <- df %>% drop_na(metascore)

#Confirming Current Null Values

colSums(is.na(df))

           game_title              platform          release_year             publisher             metascore        critic_reviews          user_reviews critic_compound_score 
                    0                    16                    16                     0                     0                     2                     0                     2 
  user_compound_score 
                    0 

# Dropping Null Values for critic_compound_score

df <- df %>% drop_na(critic_compound_score)

# Confirming Current Null Value Count
# I will keep the NUll Values for platform and release_year, for my hypothesis testing is not concerned with these details, only the scores for each title
colSums(is.na(df))

           game_title              platform          release_year             publisher             metascore        critic_reviews          user_reviews critic_compound_score 
                    0                    16                    16                     0                     0                     0                     0                     0 
  user_compound_score 
                    0 

#table(df['game_title'])

# Mutate new column with critc and user compound and times by 100 to create simplicity when running analysis with metascore

df_mutate <- mutate(df,
                    user_and_critic_compound_score = round((critic_compound_score * user_compound_score)*100))
df <- df_mutate
df

install.packages('plyr')

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.3/plyr_1.8.8.tgz'
Content type 'application/x-gzip' length 1028036 bytes (1003 KB)
==================================================
downloaded 1003 KB

The downloaded binary packages are in
    /var/folders/qb/kypsbnkd3x17lyrmt3wfgwph0000gn/T//RtmpCkwRAS/downloaded_packages

library(plyr)

-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
You have loaded plyr after dplyr - this is likely to cause problems.
If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
library(plyr); library(dplyr)
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

Attaching package: ‘plyr’

The following objects are masked from ‘package:dplyr’:

    arrange, count, desc, failwith, id, mutate, rename, summarise, summarize

The following object is masked from ‘package:purrr’:

    compact

ddply(df,"game_title", numcolwise(sum))

ggplot(df, aes(x=game_title,y=metascore))+ geom_bar(stat = 'identity')

ggplot(df, aes(x=game_title, fill=metascore)) + geom_bar(position='dodge')